cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
-
Journal Mail Official
jurnal.bits@gmail.com
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
Building of Informatics, Technology and Science
Published by Forum Kerjasama Pendidikan TInggi
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Computer Science & IT
Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. This journal is managed by Forum Kerjasama Pendidikan Tinggi (FKPT) published 2 times a year in Juni and Desember. The existence of this journal is expected to develop research and make a real contribution in improving research resources in the field of information technology and computers.
Arjuna Subject : -
Articles 926 Documents
 50   51   52   53   54 
Deteksi Potensi Depresi dari Unggahan Media Sosial X Menggunakan IndoBERT Situmorang, Gilbert Fernando; Purba, Ronsen
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5496

Abstract

Over the past few decades, mental disorders such as depression have increased and become a serious public health issue. Many affected individuals choose not to seek professional support due to social stigma. Social media platforms like X provide opportunities to study mental health on a large scale because users often share their personal experiences and emotions. However, there are challenges in understanding language patterns and context in posts, necessitating appropriate techniques and models to effectively detect potential depressions. Utilizing Natural Language Processing (NLP) techniques, this study analyzes 37,554 texts from social media posts to detect potential depressions. This study employs the IndoBERT model, an adaptation of BERT trained on Indonesian text data, to identify potential depression from social media texts. Data were collected through scrapping using negatively and positively connotated keywords, which were consulted with psychiatrists. The text pre-processing includes case folding, text cleaning, spell normalization, stopword removal and stemming. The data were then labeled using the IndoBERT emotion classification model, categorizing negative emotions as depression and positive emotions as normal. The model was trained and evaluated using accuracy, precision, recall, and F1-score metrics, with the best results showing an accuracy of 94.91%, precision of 94.91%, recall of 94.91%, and an F1-score of 94.91%. The results indicate that the IndoBERT model is effective in detecting potential depression from social media texts. However, there are limitations due to the reliance on social media posts, which may not fully reflect the users’ emotional conditions.
Hate Speech Classification in Tiktok Reviews using TF-IDF Feature Extraction, Differential Evolution Optimization, and Word2Vec Feature Expansion in a Classification System using Recurrent Neural Network (RNN) Fatha, Rizkialdy; Sibaroni, Yuliant; Prasetyowati, Sri Suryani
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In the ever-evolving digital era, social media, especially platforms like TikTok, has become a primary channel for users to share opinions, experiences, and expressions. However, the increasing prevalence of hate speech in reviews on the Google Play Store for the TikTok app indicates the need for a sophisticated approach to identify and classify harmful content. This research is aimed to optimize the classification of hate speech in Google Play reviews of the TikTok app by integrating Term Frequency-Inverse Document Frequency (TF-IDF), Differential Evolution, and Word2Vec within a Recurrent Neural Network (RNN) model. The TF-IDF technique will be used to extract relevant features from a review, while Differential Evolution will be applied to efficiently optimize the model parameters. The use of Word2Vec will enhance the representation of words in the context of app reviews, whereas the RNN model will enable the recognition of temporal patterns in hate speech. The results of this research are expected to contribute significantly to the improvement of hate speech classification on digital platforms focused on app reviews.
Implementasi Algoritma SVM Non-Linear Pada Klasifikasi Analisis Sentimen Perkembangan AI di Sektor Pendidikan Putri, Alda Nabila; Aryanti, Aryanti; Soim, Sopian
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

As technology advances, the utilization of the X platform or formerly Twitter is expanding, allowing users to exchange opinions on various topics including the transformative impact of AI in the Education sector. While AI has great potential in revolutionizing the quality and accessibility of education, it can also bring potential challenges, such as over-reliance on technology. Sentiment analysis is a computational approach to identify, extract, and classify sentiments, opinions, and emotions expressed in text. To examine the problem, this research implements a Non-Linear Support Vector Machine model to analyze sentiment about AI in the education sector. This study built four SVM models with different kernel functions, namely linear, RBF, Polynomial, and Sigmoid kernels. By utilizing 3,000 tweet data collected from platform X by scraping technique, the SVM model with polynomial kernel succeeded in becoming the best model, with accuracy, precision, recall and f1-score values of 92%. This model was able to classify 52.9% of the tweet data with positive sentiment and 47.1% of the tweet data with negative sentiment, which shows that in general, users of platform X tend to have a positive sentiment towards the development of AI in the education sector.
Implementation of K-Means Clustering Algorithm to Determine the Best-Selling Snack In Purwokerto MSMES Ayuni, Ratih; Berlilana, Berlilana
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5524

Abstract

This research was conducted to provide information related to the sale of existing MSME snacks, which products have many buyers and which are not, besides that this research can provide a view for the sale of various snacks whether they are still sold or selling the same snacks but with new innovations so that there are many enthusiasts. To do this, a grouping is needed, therefore the researcher chooses a k-means algorithm which will later be used for the clustering process. The grouping is divided into two, namely best-selling and under-selling products, for research data collected from January to March 2024. Then the data used includes the name of the snack, the number of stocks and the number of sales. After calculating the results of this study, the k-means algorithm performs a calculation of as many as two rounds so as to form two clusters where in cluster one the names of snacks that sell well are grouped such as cimol, noodle skewers, dimsum, egg rolls and white bread. Then in cluster two, the less selling product falls to seblak snacks so that seblak snacks can make new innovations to sell better and can compete with other products. This research succeeded in grouping and providing an overview of products that sell well or not, for future research can be reproduced related to the data used.
Analisis Sentimen Pengguna Aplikasi Bukalapak di Platform Playstore Menggunakan Metode Naïve Bayes Subhan Mahendrasyah, Muhammad; Hariguna, Taqwa
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5528

Abstract

Indonesia, as a country with significant growth in internet users, recorded a 7.3% digital economy contribution to GDP in 2017, surpassing the overall economic growth of 5.1%. One of the main challenges is efficiency in managing user reviews to improve services, as done by Bukalapak app using data scraping to collect 5000 reviews. This study uses the Naïve Bayes algorithm to analyze the sentiment of Bukalapak app user reviews, focusing on identifying positive and negative sentiment patterns. The goal is to deepen the understanding of user perceptions of Bukalapak services and provide a basis for strategic decision-making in improving user experience and application services. The Naïve Bayes algorithm in this study achieved an accuracy rate of 67.9%, with 13.3% of reviews found to be positive and 86.7% of reviews negative. The analysis results highlight the importance of improvements in certain aspects of Bukalapak's services, which can lead to further development to increase user satisfaction. The majority of Bukalapak reviews indicate shortcomings or criticism of its services, which highlights the importance of improvement in certain aspects. The Naïve Bayes model provides a clear understanding of user sentiment, which is key in strategic decision-making and efforts to improve user experience on the Bukalapak platform. Thus, this research makes an important contribution in directing further improvement and development steps in enhancing Bukalapak app services as well as better understanding user perceptions.
Perancangan Helm Pintar dengan Fitur Keselamatan Deteksi Kantuk Berbasis NodeMCU dan Accelerometer Julianti, Amelia; Salamah, Irma; Hesti, Emilia
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5534

Abstract

Driving safety is a major focus given the high number of accidents caused by drowsy drivers. This article discusses the design of a smart helmet that detects drowsiness to improve rider safety. The smart helmet integrates technology with drowsiness detection to reduce the risk of accidents and provide a safer driving experience. The system uses NodeMCU and MPU6050 Accelerometer to monitor head movement, activating an alarm if the head moves more than 5 degrees, which indicates drowsiness or loss of focus. It is expected that the risk of accidents due to drowsiness can be significantly reduced with this approach. The test results show that the system is able to effectively detect unusual head movements and provide a quick alarm response, thus improving driving safety as expected. In the context of this measurement, the lower error values of 0.70% and 1.18% indicate that the MPU6050 sensor provides more accurate results in measuring the angle against a given reference angle. The angle measurement results between the reference and the MPU6050 sensor show that the value obtained from the sensor is not much different from the reference angle. Although there is a slight difference, the accuracy of the MPU6050 is still reliable for practical purposes, showing consistent performance and close to the actual value. This indicates that the MPU6050 sensor is capable of providing quite precise results, so it can be used as an effective angle measuring device in various applications. The integration of this sensor into smart helmets enables early detection of signs of drowsiness, which can then activate automatic alerts to improve driver safety. Test results also demonstrated the helmet's ability to monitor and send real-time data to ThingSpeak, providing easy-to-understand visualizations, historical data storage, and automatic notifications when signs of drowsiness are detected.
Personal Training with Tai Chi: Classifying Movement using Mediapipe Pose Estimation and LSTM Suhandi, Vartin; Santoso, Handri
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5536

Abstract

This research aims to tackle challenges in the practice of Tai Chi Bafa Wubu (BWTC), where limited access to trained instructors and daily schedules hinder training consistency. The proposed approach combines Human Pose Estimation technology using Mediapipe with Long Short-Term Memory (LSTM) models to classify BWTC movements. This method utilizes video datasets collected from the internet and augmented to train LSTM models, focusing on An, Ji, and Zhou movements. Experimental results show that the model can predict movements with high accuracy in training and direct user trials. The development of these techniques facilitates more effective self-training in Tai Chi, leveraging advanced AI technology to improve movement supervision and user movement interpretation accuracy. This study not only offers a practical solution to enhance Tai Chi training efficiency and accessibility but also explores the potential application of pose estimation technology and machine learning in broader sports movement monitoring and evaluation. It is expected that this research will make a significant contribution to health and fitness by enabling individuals to independently practice Tai Chi with technological guidance, promoting better mental and physical health among the general public.
Perbandingan Prediksi Penyakit Stunting Balita Menggunakan Algoritma Support Vektor Machine dan Random Forest Wiratama, Yunada; Aziz, RZ Abdul
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5543

Abstract

Stunting in toddlers is a serious health problem, especially in developing countries, where toddlers experience stunted growth due to chronic malnutrition. This condition not only affects the child's height but also their cognitive development and overall health. Identifying risk factors and classifying stunting can help in addressing and preventing this issue. In this study, we applied two machine learning methods to compare which one performs better in classification, namely Random Forest and Support Vector Machine (SVM), to classify stunting in toddlers. The data used is public data consisting of 97,873 entries. After undergoing preprocessing steps such as data cleaning, normalization, and splitting, the data was divided into training and testing sets. The Random Forest and SVM models were then trained using the training set and evaluated using metrics such as accuracy, precision, and recall. The analysis results showed that both methods perform well in classifying stunting in toddlers, with Random Forest achieving an accuracy of 0.9997 and SVM achieving an accuracy of 0.9951. These findings are expected to aid in the development of more effective intervention strategies to address stunting in toddlers. With this approach, it is hoped to make a significant contribution to reducing the prevalence of stunting in developing countries and improving the quality of life for children in the future. Additionally, this research opens opportunities for further exploration of other machine learning techniques for other health issues.
Prediksi Kabut Bandar Udara di Indonesia Menggunakan Neural Network dan Radom Forest Kurniawan, Agustinus; Abdul Aziz, RZ
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5544

Abstract

Fog at airports greatly disrupts flight operations, limiting visibility and thus having a significant impact on flight operations such as taxiing, takeoff and landing. The biggest challenge in fog prediction is the inconsistent and chaotic complexity of atmospheric processes. This research uses the Neural Network algorithm and random forest algorithm to predict fog at Radin Inten II Airport in Lampung. The data used in this study include 14 weather attributes collected hourly from 2020 to 2024. Meteorological variables analyzed include dry bulb temperature, wet bulb temperature, dew point, relative humidity, barometric pressure QFE and QFF, and fog-related weather conditions . The predictive model was optimized by hyperparameter tuning including optimizer selection (SGD, Adam), learning rate ( 0.001), and number of epochs ( 300). The research results show that the random forest model with optimal configuration provides the highest accuracy of 69.44% in fog prediction. The Backpropagasi Neural Network also shows good performance well with an accuracy of 67.23%. By using this model, fog predictions can be made more accurate and faster, providing significant benefits to aviation safety. This research highlights the importance of using diverse data and rigorous evaluation methods to create reliable and effective weather prediction models.
Effective Coronary Artery Disease Prediction Using Bayesian Optimization Algorithm and Random Forest Amrullah, Muhammad Syiarul; Yuniarti, Anny
Building of Informatics, Technology and Science (BITS) Vol 6 No 2 (2024): September 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v6i2.5554

Abstract

Coronary artery disease (CAD) continues to be a major global health issue, demanding more effective diagnostic techniques. This study introduces a detailed framework for CAD detection that integrates data preprocessing, feature engineering, and model optimization to enhance diagnostic accuracy. Our methodology encompasses comprehensive data cleansing to eliminate inconsistencies, transformations for better feature representation, feature reduction to highlight relevant variables, data augmentation for balanced class distribution, and optimization strategies to boost model performance. We employed a random forest classifier, trained via 5-fold cross-validation, to develop a robust model. The efficacy of this model was tested through two key experiments: firstly, by comparing its performance on preprocessed versus raw data, and secondly, against previous studies. Results demonstrate that our model significantly surpasses the one trained on raw data, achieving an accuracy of 93.00% compared to 86.16%. Moreover, when compared with existing research, our random forest model excels with an accuracy of 93.00%, a F1 Score of 93.00%, and a recall of 94.00%. Despite the superior precision of the Hybrid PSO-EmNN model found in other research, our results are promising. They underscore the potential of advanced feature engineering to further refine the effectiveness of CAD detection models. The study concludes that meticulous data preprocessing and model optimization are crucial for enhancing CAD diagnostics. Future research should focus on incorporating more sophisticated feature engineering techniques and expanding the dataset to improve the model’s precision and overall diagnostic capabilities.

Page 52 of 93 | Total Record : 926

 50   51   52   53   54 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 7 No 3 (2025): December 2025 Vol 7 No 2 (2025): September 2025 Vol 7 No 1 (2025): June (2025) Vol 6 No 4 (2025): March 2025 Vol 6 No 3 (2024): December 2024 Vol 6 No 2 (2024): September 2024 Vol 6 No 1 (2024): June 2024 Vol 5 No 4 (2024): March 2024 Vol 5 No 3 (2023): December 2023 Vol 5 No 2 (2023): September 2023 Vol 5 No 1 (2023): June 2023 Vol 4 No 4 (2023): March 2023 Vol 4 No 3 (2022): December 2022 Vol 4 No 2 (2022): September 2022 Vol 4 No 1 (2022): June 2022 Vol 3 No 4 (2022): March 2022 Vol 3 No 3 (2021): December 2021 Vol 3 No 2 (2021): September 2021 Vol 3 No 1 (2021): June 2021 Vol 2 No 2 (2020): December 2020 Vol 2 No 1 (2020): June 2020 Vol 1 No 2 (2019): December 2019 Vol 1 No 1 (2019): June 2019 Vol 1 No 1 (2019): Edisi Juni More Issue